3/30/2026
20% of vulnerability AI-patches that pass CI break production. Here's why
Analysis of AI-generated patches passing CI tests but failing production. 20% breakage rate in vulnerability fixes.
3/30/2026
Show HN: LLMinate LLM Detector
Title only, no content. Tool for detecting LLM-generated text.
3/30/2026
Three-processor inference on AMD Ryzen AI 300
Brief mention of AMD Ryzen AI 300 processor inference capabilities without technical details.
3/30/2026
Give your AI agent a real email address (open source, Cloudflare)
Open source email infrastructure for AI agents. Send, receive, search, extract codes. Deploy on Cloudflare. Integrates with Claude Code and AI agent platforms.
3/30/2026
Show HN: We Built 450 Modular Agent Skills for Medical Research
Open source library of 450+ modular agent skills for medical research. Works with OpenClaw, Claude with scientific integrity constraints.
3/30/2026
Show HN: Smux – split terminals for AI agents
Open source macOS terminal multiplexer for running AI agents in parallel with notifications. Built for agent workflows.
3/30/2026
Stripe stole $85k and closed our account
Founder dispute over Stripe account closure for AI image/video generation platform citing payment reversal policy.
3/30/2026
You're right to be anxious about AI: This is how much we are building
Analysis of accelerating AI tool/framework releases tracked via HN, GitHub, npm, PyPI showing ecosystem growth rate.
3/30/2026
Mathematical methods and human thought in the age of AI
Philosophy preprint on mathematical methods and AI's role in mathematics formalization and human thought.
3/30/2026
Show HN: Veil – A Minimal Neovim GUI for macOS with Metal Rendering
Neovim GUI for macOS using Metal GPU rendering with multi-window support and IME for CJK input.
3/30/2026
Selling to AI Agents
Analysis of how AI agents integrate third-party tools into code generation and product decision workflows.
3/30/2026
Fast Image AI Image Enhancer
Marketing content for commercial AI image upscaler/enhancement tool with no technical details.
3/30/2026
AI Website Redesign Benchmark
Website redesign benchmark comparing four AI models for generating website designs from URLs.
3/30/2026
Adding verification steps to AI agents made them worse. I tested it 29 times
Empirical study showing verification steps degraded AI agent performance across 29 tests. Original experimental research.
3/30/2026
APIEval-20: A Benchmark for Black-Box API Test Suite Generation
APIEval-20 benchmark dataset for evaluating black-box API test suite generation using LLMs and schemas.
3/30/2026
Subnautica 2 publisher's CEO used ChatGPT to fire studio head and failed
CEO used ChatGPT to terminate studio head; decision was reversed and criticized.
3/30/2026
Show HN: NVSonar – tells why your GPU is slow, not just utilization percentage
GPU profiling tool that diagnoses performance bottlenecks beyond utilization metrics. Minimal details provided but relevant tool.
3/30/2026
I built an MCP server so your agent stops picking the wrong cloud services
MCP server for AI agents to select appropriate cloud services with current pricing and compatibility data. 74 services, no API key required.
3/30/2026
Stanford study reveals AI vision models invent images they never see
Stanford research showing AI vision models generate images not in training data through hallucination mechanisms.
3/30/2026
President Trump Gaggles with Press on Air Force One En Route
News about President Trump press interaction on Air Force One.
3/30/2026
Tribe v2: Predictive Foundation Model on Human Brain Processing Complex Stimuli
TRIBE v2: Predictive AI model of human brain responses to visual, auditory, and language stimuli from neuroscience research.
3/30/2026
HD Audio Driver for Windows 98SE / Me
HD Audio driver for Windows 98SE/ME systems on Intel chipsets with WDM support.
3/30/2026
Excel2r – R package that migrates Excel workbooks to standalone R scripts
R package that converts Excel workbooks to standalone R scripts with formula recreation and verification against cached values.
3/30/2026
LLMnesia – Local-first search across your AI conversations
LLMnesia: Local-first search tool for AI conversation history across ChatGPT, Claude, Gemini, and other platforms.
3/30/2026
Meta's court losses spell potential trouble for AI research, consumer safety
Analysis of Meta's legal losses and liability implications from internal social science research on platform effects.
3/30/2026
Show HN: Free, Open-Source WhisperFlow That Just Works
WhisperFlow: Free, open-source speech-to-text tool for macOS. On-device processing, no cloud upload, no account required.
3/30/2026
Any4D: Open-Prompt 4D Generation from Natural Language and Images
arXiv research on 4D generation from natural language and images using embodied world models. Addresses data scarcity and long-horizon video generation challenges.
3/30/2026
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
arXiv research proposing Balanced Fine-Tuning method for aligning LLMs with biomedical knowledge. Combines SFT and RL using confidence-weighted token optimization for scientific understanding.
3/30/2026
StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
arXiv research on streaming video understanding with gaze signal interpretation for AR applications. Evaluates multimodal LLMs on temporal reasoning with human attention signals.
3/30/2026
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
arXiv research on multimodal memory architecture for long-form video understanding. Addresses context capacity and visual detail retention in hours-long videos using dynamic memory mechanisms.
3/30/2026
Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
Post-training method for lower-resource languages preserving fluency when aligned by disfluent reward models, addressing preference optimization data scarcity.
3/30/2026
Particulate: Feed-Forward 3D Object Articulation
Feed-forward transformer model predicting 3D object articulations including parts, kinematic structure, and motion constraints for articulated object understanding.
3/30/2026
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Cascaded reinforcement learning infrastructure for scaling general-purpose reasoning models, addressing heterogeneity in response lengths and verification latency.
3/30/2026
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
SonicMoE optimizes Mixture of Experts model inference through IO and tile-aware techniques, accelerating high-sparsity MoE architectures for language models.
3/30/2026
PathFinder: Advancing Path Loss Prediction for Single-to-Multi-Transmitter Scenario
Deep learning method for radio path loss prediction in multi-transmitter 5G scenarios, addressing distribution shifts and environmental generalization.
3/30/2026
Dual-objective Language Models: Training Efficiency Without Overfitting
Dual-objective language model combining autoregressive and masked-diffusion training without architectural changes, improving efficiency and reducing overfitting.
3/30/2026
MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation
Medical report generation using reinforcement learning with clinical alignment objectives, improving correctness over token-level likelihood training approaches.
3/30/2026
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Study comparing SpeechLLMs that directly process speech for translation against cascaded transcription pipelines, evaluating speech modality integration effectiveness.
3/30/2026
The Dual-State Architecture for Reliable LLM Agents
Dual-State Architecture formalizes execution primitives coupling stochastic LLM generation with deterministic verification guards for reliable code generation agents.
3/30/2026
RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution
Benchmark evaluating LiDAR 3D perception model robustness under simultaneous domain shifts and label-space evolution in autonomous driving scenarios.
3/30/2026
Incorporating Q&A Nuggets into Retrieval-Augmented Generation
Crucible system augments RAG with Q&A nuggets from documents, preserving citation provenance and improving extraction, selection, and report generation.
3/30/2026
Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets?
Study examining risks of RAG system evaluation and optimization using LLM judges, revealing circularity issues in nugget-based evaluation approaches.
3/30/2026
CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models
CARPE method improving vision-centric capabilities of vision-language models through context-aware image representation prioritization via ensemble approach.
3/30/2026
NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
Framework addressing LLM's tendency to collapse ambiguous inputs prematurely by mapping text to non-collapsing state spaces for better dialogue reasoning.
3/30/2026
AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
Study introducing VAPT toolkit to evaluate how LLMs extract, embody, and explain human values from conversations through user perception research.
3/30/2026
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
Benchmark for evaluating multimodal LLMs on handwritten STEM student solutions with mathematical formulas and diagrams, addressing authentic domain-specific evaluation gaps.
3/30/2026
TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
TernaryLM: Language model trained natively with 1.5-bit quantization achieving memory-efficient deployment on edge devices while maintaining language modeling capability.
3/30/2026
PISCO: Precise Video Instance Insertion with Sparse Control
Video generation model for precise instance insertion with sparse control in filmmaking applications, moving beyond prompt-engineering toward controllable generation.
3/30/2026
SWE Context Bench: A Benchmark for Context Learning in Coding
Benchmark evaluating LLM-based coding agents on their ability to learn from context and reuse experience across related software engineering tasks in repositories.
3/30/2026
Administrative Law's Fourth Settlement: AI and the Capability-Accountability Trap
Administrative law analysis of how government agencies balance technological capability with democratic oversight and accountability mechanisms.